Evanston Open Data Research
This file is for exploratory research for Northwestern University’s City of Evanston Open Data Contest: https://sites.northwestern.edu/lovedataweek/contest/
Deadline: Monday, April 1 @ 3:00 PM
## Libraries
library(ggplot2)
library(ggmap)## Google's Terms of Service: https://cloud.google.com/maps-platform/terms/.## Please cite ggmap if you use it! See citation("ggmap") for details.library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.2.1 ──## ✔ tibble 2.0.0 ✔ purrr 0.2.5
## ✔ tidyr 0.8.2 ✔ dplyr 0.7.8
## ✔ readr 1.3.0 ✔ stringr 1.3.1
## ✔ tibble 2.0.0 ✔ forcats 0.3.0## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(leaflet)
library(leaflet.extras)
library(htmlwidgets)
library(rgdal)## Loading required package: sp## rgdal: version: 1.3-6, (SVN revision 773)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 2.1.3, released 2017/20/01
## Path to GDAL shared files: /Library/Frameworks/R.framework/Versions/3.4/Resources/library/rgdal/gdal
## GDAL binary built with GEOS: FALSE
## Loaded PROJ.4 runtime: Rel. 4.9.3, 15 August 2016, [PJ_VERSION: 493]
## Path to PROJ.4 shared files: /Library/Frameworks/R.framework/Versions/3.4/Resources/library/rgdal/proj
## Linking to sp version: 1.3-1theme_set(theme_linedraw())Traffic Stops 2017-2018
traffic_data <- read.csv("https://data.cityofevanston.org/resource/bbbk-a8vu.csv?$limit=35000")
levels(traffic_data$day_of_the_week) <- c("Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun")Stops by Day of Week/Race
traffic_data %>%
ggplot() +
geom_bar(aes(day_of_the_week)) +
facet_wrap(~race)
#### Stops by Race/Beat
traffic_data %>%
ggplot() +
geom_bar(aes(race)) +
facet_wrap(~police_beat)
## Evanston Arrests
arrest_data <- read.csv("https://data.cityofevanston.org/resource/jwmg-4gbx.csv")
arrest_data$loc <- as.character(arrest_data$location)
arrest_data <- arrest_data %>%
drop_na(loc)
arrest_data$loc <- arrest_data$loc %>%
substring(8)
arrest_data$loc <- arrest_data$loc %>%
str_sub(1, str_length(arrest_data$loc)-1)
arrest_data_lonlat <- arrest_data %>%
separate(col = loc, c("lon", "lat"), sep = " ")## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 76 rows [38,
## 361, 363, 367, 390, 394, 396, 397, 400, 415, 417, 418, 421, 422, 426, 427,
## 428, 429, 447, 451, ...].arrest_data_lonlat$lon <- as.numeric(arrest_data_lonlat$lon)
arrest_data_lonlat$lat <- as.numeric(arrest_data_lonlat$lat)
arrest_data_lonlat <- arrest_data_lonlat %>%
drop_na(lat)Mapping Arrests in Evanston
This is a map of arrests made in Evanston.
leaflet() %>%
addCircleMarkers(lng=arrest_data_lonlat$lon, lat=arrest_data_lonlat$lat, popup = arrest_data_lonlat$arrest_type) %>%
addProviderTiles(providers$CartoDB.Positron)This is a heatmap of arrests made in Evanston.
leaflet(arrest_data_lonlat) %>%
addProviderTiles(providers$CartoDB.DarkMatter) %>%
addHeatmap(lng = ~lon, lat = ~lat,
blur = 30, max = 0.05, radius = 15)All Evanston Police Activity
pdata <- read.csv("https://data.cityofevanston.org/resource/t5g5-xgby.csv?$limit=200000")
pdata$location <- as.character(pdata$location)
pdata <- pdata %>%
filter(location != "")
pdata$loc <- pdata$location
pdata$loc <- pdata$loc %>%
substring(8)
pdata$loc <- pdata$loc %>%
str_sub(1, str_length(pdata$loc)-1)
pdata <- pdata %>%
separate(col = loc, c("lon", "lat"), sep = " ")
pdata$lon <- as.numeric(pdata$lon)
pdata$lat <- as.numeric(pdata$lat)This is a heatmap of all police activity in Evanston.
pdata %>%
leaflet() %>%
addProviderTiles(providers$CartoDB.DarkMatter) %>%
addHeatmap(lng = ~lon, lat = ~lat,
blur = 20, radius = 8) Tree Information
## Read in Data
tdata <- read.csv("Trees_data.csv")
##Set Geo
tdata$location <- as.character(tdata$the_geom)
tdata <- tdata %>%
filter(location != "")
tdata$loc <- tdata$location
tdata$loc <- tdata$loc %>%
substring(8)
tdata$loc <- tdata$loc %>%
str_sub(1, str_length(tdata$loc)-1)
tdata <- tdata %>%
separate(col = loc, c("lon", "lat"), sep = " ")
tdata$lon <- as.numeric(tdata$lon)
tdata$lat <- as.numeric(tdata$lat)Types of Trees
tdata %>%
group_by(Species) %>%
count(sort=TRUE) %>%
head(30)Stop and Frisk
Data from https://data.cityofevanston.org/browse?q=Stop%20and%20Frisk&sortBy=relevance
sfdata <- read.csv("Stop_and_Frisk.csv")By Race
sfdata %>%
group_by(Race) %>%
ggplot(aes(Race)) +
geom_bar() +
coord_flip() +
scale_y_continuous(expand = c(0,0), limits = c(0, 1300)) 
By Reason
sfdata %>%
mutate(Reason.Code.Description = fct_rev(fct_infreq(Reason.Code.Description))) %>%
ggplot(aes(Reason.Code.Description)) +
geom_bar() +
coord_flip() +
scale_y_continuous(expand = c(0,0))
sfdata %>%
group_by(Race) %>%
ggplot(aes(Race)) +
geom_bar() +
coord_flip() +
facet_grid(~Enforcement) +
scale_y_continuous(expand = c(0,0))
sfdata %>%
filter(grepl('STREET', Reason.Code.Description)) %>%
ggplot(aes(Race, Age)) +
geom_violin()## Warning: Removed 3 rows containing non-finite values (stat_ydensity).
sfdata %>%
group_by(Reason.Code.Description, Enforcement) %>%
summarise (n = n()) %>%
mutate(freq = n / sum(n)) %>%
filter(Enforcement == "ARREST") %>%
print(n=15)## # A tibble: 15 x 4
## # Groups: Reason.Code.Description [15]
## Reason.Code.Description Enforcement n freq
## <fct> <fct> <int> <dbl>
## 1 GANG NARC/RSO ARREST 4 0.571
## 2 GANG/NARCOTIC ARREST 11 0.275
## 3 OTHER ARREST 22 0.186
## 4 STREET STOP ARREST 35 0.145
## 5 STREET STOP/GANG NARC ARREST 7 0.115
## 6 STREET STOP/RSO ARREST 1 0.333
## 7 STREET STOP/SUSP PERSON ARREST 9 0.0744
## 8 STREET STOP/SUSP PERSON/GANG NARC ARREST 3 0.115
## 9 SUSP PERSON/GANG NARC ARREST 3 0.273
## 10 SUSPICIOUS PERSON ARREST 2 0.0426
## 11 TRAF STOP/GANG NARC ARREST 30 0.0804
## 12 TRAF STOP/GANG NARC/RSO ARREST 1 0.0769
## 13 TRAF STOP/SUSP PERS/GANG NARC ARREST 2 0.4
## 14 TRAF STOP/SUSP PERSON/GANG/RSO ARREST 4 0.0816
## 15 TRAFFIC STOP ARREST 78 0.138sfdata %>%
group_by(Race, Enforcement) %>%
summarise (n = n()) %>%
mutate(freq = n / sum(n)) %>%
filter(Enforcement == "ARREST")Evanston Population Overall
pop <- read.csv("https://data.cityofevanston.org/resource/j228-4hwk.csv")Evanston Salary Information
saldata <- read.csv("https://data.cityofevanston.org/resource/qehy-v72q.csv")saldata %>%
arrange(desc(earnings_amount))Evanston Restaurant Info
## Food Establishment Businesses with Inspections 2018-2019
restdata <- read.csv("https://data.cityofevanston.org/resource/x9f3-wjav.csv")
### Get Lat and Lon from Point
restdata$location <- as.character(restdata$location)
restdata <- restdata %>%
filter(location != "")
restdata$loc <- restdata$location
restdata$loc <- restdata$loc %>%
substring(8)
restdata$loc <- restdata$loc %>%
str_sub(1, str_length(restdata$loc)-1)
restdata <- restdata %>%
separate(col = loc, c("lon", "lat"), sep = " ")
restdata$lon <- as.numeric(restdata$lon)
restdata$lat <- as.numeric(restdata$lat)
## Food Establishment Violations
viodata <- read.csv("https://data.cityofevanston.org/resource/rgdf-vw4g.csv")
## Food Establishment Inspections
inspdata<- read.csv("https://data.cityofevanston.org/resource/dj7x-d2cq.csv")
inspdata$inspection_date <- as.Date(as.character(inspdata$inspection_date))Join data
jresdata <- inner_join(restdata, inspdata)## Joining, by = "business_license"## Warning: Column `business_license` joining factors with different levels,
## coercing to character vectorjresdata %>%
group_by(business_license) %>%
slice(which.max(inspection_date))Map most recent scores
pal <- colorNumeric("RdYlBu", domain = jresdata$inspection_score)
leaflet() %>%
addCircleMarkers(lng=jresdata$lon, lat=jresdata$lat, popup = jresdata$business_name, stroke = FALSE, fillColor = pal(jresdata$inspection_score)) %>%
addProviderTiles(providers$CartoDB.Positron)